|
Abstract:
|
In many applications, spatial data are typically collected at areal levels (i.e., block data), while inferences and predictions are desired about the variable at points or blocks different from those at which the variable has been observed. The inferences and predictions typically depend on integrals those are often analytically intractable, and numerically expensive to approximate to high levels of accuracy. One may consider a naive approach to analyzing block data by converting it to a point-referenced counterpart by assuming that the whole mass (i.e., the integrated value) is observed at the centroid of each block. Such simplifications completely avoid the computational complexity associated with the analysis of change of support problems. In this work we assess the extent to which both the block design and underlying process properties can affect the accuracy and stability of estimation and prediction tasks performed using this misspecification (relative to when these tasks are performed using a correctly specified observational model), and provide guidance for practitioners as to when this misspecification is inappropriate.
|
